TY - GEN
T1 - Apply Masked-attention Mask Transformer to Instance Segmentation in Pathology Images
AU - Sheng, Jia Chun
AU - Liao, Yi Sheng
AU - Huang, Chun Rong
N1 - Funding Information:
This work was supported in part by the National Science and Technology Council of Taiwan under Grant NSTC 111-2634-F-006-012, NSTC 111-2628-E-006-011-MY3 and NSTC 112-2622-8-006-009-TE1.
Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Instance segmentation can be applied for the discrimination and diagnosis of cancer cells in pathology images. Accurate segmentation of each pathological cell in the pathology images can improve the efficiency of clinical diagnosis. In this paper, we aim to evaluate the state-of-the-art transformer-based instance segmentation method, masked-attention mask transformer (Mask2Former)[1], on pathology datasets. With the pretrained model of Mask2Former on the natural image instance segmentation dataset, we show that Mask2Former can be adaptive to small pathological datasets and achieve comparable or even better instance segmentation performance compared with the state-of-the-art task-specific pathology image instance segmentation methods.
AB - Instance segmentation can be applied for the discrimination and diagnosis of cancer cells in pathology images. Accurate segmentation of each pathological cell in the pathology images can improve the efficiency of clinical diagnosis. In this paper, we aim to evaluate the state-of-the-art transformer-based instance segmentation method, masked-attention mask transformer (Mask2Former)[1], on pathology datasets. With the pretrained model of Mask2Former on the natural image instance segmentation dataset, we show that Mask2Former can be adaptive to small pathological datasets and achieve comparable or even better instance segmentation performance compared with the state-of-the-art task-specific pathology image instance segmentation methods.
UR - http://www.scopus.com/inward/record.url?scp=85171435443&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85171435443&partnerID=8YFLogxK
U2 - 10.1109/IS3C57901.2023.00098
DO - 10.1109/IS3C57901.2023.00098
M3 - Conference contribution
AN - SCOPUS:85171435443
T3 - Proceedings - 2023 6th International Symposium on Computer, Consumer and Control, IS3C 2023
SP - 342
EP - 345
BT - Proceedings - 2023 6th International Symposium on Computer, Consumer and Control, IS3C 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 6th International Symposium on Computer, Consumer and Control, IS3C 2023
Y2 - 30 June 2023 through 3 July 2023
ER -
